-
公开(公告)号：US20140125666A1
公开(公告)日：2014-05-08
申请号：US13905400
申请日：2013-05-30
Inventor： Jun Yong Noh , Kye Hyun Kim , Jung Jin Lee , Young Hui Kim , Sang Woo Lee , Kyung Han Lee
IPC: G06T15/40
CPC classification number: G06T7/536 , H04N13/128 , H04N2013/0081
Abstract: There are provided a method and an apparatus for generating a depth map of a stereoscopic image that are capable of representing the depth perception of an image more finely by considering not only vanishing points but also fine lines formed within an image. The method includes: generating multiple line segments by grouping multiple edge pixels within an input image based on an intensity gradient direction; merging the multiple line segments based on similarity and thereafter detecting at least one vanishing point in consideration of a result of the merging; and generating an energy depth function on which correlation between the line segments and the vanishing point is reflected and generating a depth map by decoding the energy depth function.
Abstract translation: 提供了一种用于生成立体图像的深度图的方法和装置，其能够通过不仅考虑消失点而且还考虑在图像内形成的细纹，更精细地表示图像的深度感知。 该方法包括：通过基于强度梯度方向对输入图像内的多个边缘像素进行分组来生成多个线段; 基于相似度合并多个线段，然后考虑到合并的结果来检测至少一个消失点; 并产生能量深度函数，在该能量深度函数上反映线段和消失点之间的相关性，并通过解码能量深度函数产生深度图。
-
公开(公告)号：US20180268583A1
公开(公告)日：2018-09-20
申请号：US15460461
申请日：2017-03-16
Inventor： Jun Yong Noh , Young Hui Kim , Kye Hyun Kim
IPC: G06T11/60 , H04N19/426 , H04N19/136 , H04N19/182 , H04N19/93
CPC classification number: G06T11/60 , H04N19/136 , H04N19/182 , H04N19/426 , H04N19/463 , H04N19/597 , H04N19/93
Abstract: Provided is a method for generating a single representative image from multi-view images, in which multi-view images captured from two or more viewpoints are combined into a single image using depth information, including identifying visible information from different viewpoints for pixels in each view image using depth information, identifying context of the pixels in all viewpoints using the acquired visible information and the depth information, and combining into a single image, compressing the combined image based on color information, and compressing viewpoint information of pixels in the compressed image.
-
公开(公告)号：US09445074B2
公开(公告)日：2016-09-13
申请号：US13905418
申请日：2013-05-30
Inventor： Jun Yong Noh , Sang Woo Lee , Young Hui Kim , Jung Jin Lee , Kye Hyun Kim , Kyung Han Lee
IPC: H04N13/00
CPC classification number: H04N13/128
Abstract: Provided are an apparatus and a method for manipulating depth of a stereoscopic image that enable a user to manipulate depth of a stereoscopic image easily and intuitively. The apparatus may include: a histogram analyzing unit acquiring a depth distribution chart by performing histogram analysis of a disparity map corresponding to an input image; a Gaussian mixture model (GMM) fitting unit acquiring multiple depth layers by performing GMM fitting of the depth distribution chart; a disparity adjusting unit adjusting at least one of a position and a volume of at least one of the multiple depth layers and calculating a disparity mapping function on which a result of the adjustment is reflected in response to a user request; and a disparity map recalculating unit calculating a new disparity map by optimizing the disparity mapping function.
Abstract translation: 提供了一种用于操纵立体图像的深度的装置和方法，其使用户能够容易且直观地操纵立体图像的深度。 该装置可以包括：直方图分析单元，通过对与输入图像相对应的视差图进行直方图分析来获取深度分布图; 高斯混合模型（GMM）拟合单元通过深度分布图的GMM拟合获取多个深度层; 视差调整单元，其调整所述多个深度层中的至少一个深度层的位置和体积中的至少一个，并且计算响应于用户请求反映所述调整结果的视差映射函数; 以及视差图重新计算单元，通过优化视差映射函数来计算新的视差图。
-
公开(公告)号：US20140118507A1
公开(公告)日：2014-05-01
申请号：US13905418
申请日：2013-05-30
Inventor： Jun Yong Noh , Sang Woo Lee , Young Hui Kim , Jung Jin Lee , Kye Hyun Kim , Kyung Han Lee
IPC: H04N13/00
CPC classification number: H04N13/128
Abstract: Provided are an apparatus and a method for manipulating depth of a stereoscopic image that enable a user to manipulate depth of a stereoscopic image easily and intuitively. The apparatus may include: a histogram analyzing unit acquiring a depth distribution chart by performing histogram analysis of a disparity map corresponding to an input image; a Gaussian mixture model (GMM) fitting unit acquiring multiple depth layers by performing GMM fitting of the depth distribution chart; a disparity adjusting unit adjusting at least one of a position and a volume of at least one of the multiple depth layers and calculating a disparity mapping function on which a result of the adjustment is reflected in response to a user request; and a disparity map recalculating unit calculating a new disparity map by optimizing the disparity mapping function.
Abstract translation: 提供了一种用于操纵立体图像的深度的装置和方法，其使用户能够容易且直观地操纵立体图像的深度。 该装置可以包括：直方图分析单元，通过对与输入图像相对应的视差图进行直方图分析来获取深度分布图; 高斯混合模型（GMM）拟合单元通过深度分布图的GMM拟合获取多个深度层; 视差调整单元，其调整所述多个深度层中的至少一个深度层的位置和体积中的至少一个，并且计算响应于用户请求反映所述调整结果的视差映射函数; 以及视差图重新计算单元，通过优化视差映射函数来计算新的视差图。
-
-
-
Search Results
4
records
(took 0.017 seconds)
